Classification of Sprain and Non-sprain Motion using Deep Learning Neural Networks for Ankle Sprain Prevention


  • Natrisha Francis
  • Hazwani Suhaimi
  • Emeroylariffion Abas



Ankle Sprain Prevention, Time Series Classification, Long Short Term Memory Fully Convolutional Network, Class Activation Mapping


A smart wearable ankle sprain prevention device would require an intelligent monitoring system that can classify data from the sensors as sprain or non-sprain motion. This paper aims to explore Deep Neural Network method, specifically the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) for classifying sprain and non-sprain motion. A study is conducted on 11 participants to record sprain and non-sprain motions, which are used to train and test the LSTM-FCN model and previously used Support Vector Machine (SVM) model. It has been demonstrated that the LSTM-FCN model is more accurate at classifying sprain and non-sprain motion. The LSTM-FCN also proved to be more useful as its architecture allows for the Class Activation Mapping (CAM) method to be employed. The CAM method allows for the identification of temporal regions of the time series that contribute most or least to the classification decision of the LSTMFCN. Visualizing the regions of high or low contribution makes it easy to see patterns in the data correlation with sprain motion and better understand why certain non-sprain data can be misclassified as sprain motion. Overall, LSTM-FCN is found to be a viable method for the classification of sprain and non-sprain motion.


C. Doherty, E. Delahunt, B. Caulfield, J. Hertel, J. Ryan, and C. Bleakley, “The incidence and prevalence of ankle sprain injury: A systematic review and meta-analysis of prospective epidemiological studies,” Sport. Med., vol. 44, no. 1, pp. 123–140, 2014,

D. T. Fong, Y. Hong, L. Chan, P. S. Yung, and K. Chan, “A systematic review on ankle injury and ankle sprain in sports,” Sport. Med., vol. 37, no. 1, pp. 73–94, 2007.

M. P. J. van den Bekerom, G. M. M. J. Kerkhoffs, G. A. McCollum, J. D. F. Calder, and C. N. van Dijk, “Management of acute lateral ankle ligament injury in the athlete,” Knee Surgery, Sport. Traumatol. Arthrosc., vol. 21, no. 6, pp. 1390–1395, 2013,

E. Delahunt, G. F. Coughlan, B. Caulfield, E. J. Nightingale, C. W. C. Lin, and C. E. Hiller, “Inclusion criteria when investigating insufficiencies in chronic ankle instability,” Med. Sci. Sports Exerc., vol. 42, no. 11, pp. 2106–2121, 2010,

J. Hertel, “Sensorimotor deficits with ankle sprains and chronic ankle instability,” Clin. Sports Med., vol. 27, no. 3, pp. 353–370, 2008,

Y. Y. Chan et al., “Identification of ankle sprain motion from common sporting activities by dorsal foot kinematics data,” J. Biomech., vol. 43, no. 10, pp. 1965–1969, 2010,

G. Shi, C. S. Chan, W. J. Li, K. S. Leung, Y. Zou, and Y. Jin, “Mobile human airbag system for fall protection using mems sensors and embedded SVM classifier,” IEEE Sens. J., vol. 9, no. 5, pp. 495–503, 2009,

A. Sadiq, S. G. Khawaja, M. U. Akram, N. S. Alghamdi, A. Khan, and A. Shaukat, “Machine learning and signal processing based analysis of sEMG signals for daily action classification,” IEEE Access, vol. 10, pp. 40506–40516, 2022,

R. K. Begg, M. Palaniswami, and B. Owen, “Support vector machines for automated gait classification,” IEEE Trans. Biomed. Eng., vol. 52, no. 5, pp. 828–838, 2005,

K. R. Foster, R. Koprowski, and J. D. Skufca, “Machine learning, medical diagnosis, and biomedical engineering research – Commentary,” BioMedical Engineering OnLine, vol. 13, no. 1, p. 94, 2014,

F. A. Azis, H. Suhaimi, and E. Abas, “Waste classification using convolutional neural network,” Proceedings of the ACM International Conference Proceeding Series, pp. 9-13, 2020,

M. A. Humayun, H. Yassin, and P. E. Abas, “Native language identification for Indian-speakers by an ensemble of phoneme-specific, and text-independent convolutions,” Speech Commun., vol. 139, pp. 92–101, 2022,

X. Fan, T. Sun, W. Chen, and Q. Fan, “Deep neural network based environment sound classification and its implementation on hearing aid app,” Measurement, vol. 159, p. 107790, 2020,

D. Gupta, U. Kose, and O. Castillo, “Special issue on deep neural networks for biomedical data and imaging,” Expert Systems, vol. 39, no. 3, 2022,

Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015,

H. Ismail Fawaz, G. Forestier, J. Weber, L. Idoumghar, and P. A. Muller, “Deep learning for time series classification: A review,” Data Min. Knowl. Discov., vol. 33, no. 4, pp. 917–963, 2019,

F. Karim, S. Majumdar, H. Darabi, and S. Chen, “LSTM fully convolutional networks for time series classification,” IEEE Access, vol. 6, pp. 1662–1669, 2017,

A. El Mekki, A. Bouhoute, and I. Berrada, “Improving driver identification for the next-generation of in-vehicle software systems,” IEEE Trans. Veh. Technol., vol. 68, no. 8, pp. 7406–7415, 2019,

Y. Kim, J. Sa, Y. Chung, D. Park, and S. Lee, “Resource-efficient pet dog sound events classification using LSTM-FCN based on time-series data,” Sensors (Switzerland), vol. 18, no. 11, pp. 4019, 2018,

N. Rücker, L. Pflüger, and A. Maier, “Hardware failure prediction on imbalanced times series data: Generation of artificial data using Gaussian process and applying LSTMFCN to predict broken hardware,” J. Digit. Imaging, vol. 34, no. 1, pp. 182–189, 2021,

Z. Chen, X. Chen, Y. Ma, S. Guo, Y. Qin, and M. Liao, “Human posture tracking with flexible sensors for motion recognition,” Comput. Animat. Virtual Worlds, vol. 32, no. 5, pp. 1–13, 2021,

N. Francis, A. Ong, H. Suhaimi, and P. E. Abas, “A tilting platform as a sub-injury motion for ankle sprain studies,” Proceedings of the 2021 IEEE National Biomedical Engineering Conference (NBEC), 2021, pp. 117–121,

E. Preatoni et al., “The use of wearable sensors for preventing, assessing, and informing recovery from sport-related musculoskeletal injuries: A systematic scoping review,” Sensors, vol. 22, no. 9, p. 3225, 2022,

D. T. P. Fong, Y. Y. Chan, Y. Hong, P. S. H. Yung, K. Y. Fung, and K. M. Chan, “A three-pressure-sensor (3PS) system for monitoring ankle supination torque during sport motions,” J. Biomech., vol. 41, no. 11, pp. 2562–2566, 2008,

R. M. Greenwald, F. H. Simpson, and F. I. Michel, “Wrist biomechanics during snowboard falls,” Proc. Inst. Mech. Eng. Part P J. Sport. Eng. Technol., vol. 227, no. 4, pp. 244–254, 2013,

F. Karim, S. Majumdar, and H. Darabi, “Insights into lstm fully convolutional networks for time series classification,” IEEE Access, vol. 7, pp. 67718–67725, 2019,

S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” Proceedings of the 32nd International Conference on International Conference on Machine Learning (ICML’15), volume 37, 2015, pp. 448–456,

B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, “Learning deep features for discriminative localization,” Proceedings of the IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., 2016, pp. 2921–2929,

Z. Wang, W. Yan, and T. Oates, “|Time series classification from scratch with deep neural networks: A strong baseline,” Proceedings of the 2017 IEEE International Joint Conference on Neural Networks (IJCNN), 2017, vol. 57, no. 7, pp. 1578–1585,




How to Cite

Francis, N., Suhaimi, H., & Abas, E. (2023). Classification of Sprain and Non-sprain Motion using Deep Learning Neural Networks for Ankle Sprain Prevention. International Journal of Computing, 22(2), 159-169.